Skip to content
Custom Connectors
SolutionsConnectorsPricingResourcesBlog
Build my connector

Connect Nutshell to Claude Code

Make Claude log activities and move deals in Nutshell. From the terminal, inside the sessions where you already work.

Build my connectorTalk to us

How do you connect Nutshell to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Nutshell, you add a Nutshell MCP server: a small hosted service that exposes Nutshell's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Nutshell account. No API keys pasted into config files.

claude mcp add --transport http nutshell https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Nutshell once connected?

Full read-write Nutshell access lets Claude create and update leads, add and edit contacts and companies, log calls and notes against the right record, move deals between pipeline stages, and assign owners or tasks. The CRM upkeep that used to mean manual data entry happens where the pipeline already lives.

  • Create a new lead and attach it to the right contact and company
  • Log a call, note, or activity against an existing lead or contact
  • Move a deal from one pipeline stage to the next after you approve
  • Update contact or company fields to keep records current
  • Assign a lead owner or create a follow-up task for a teammate
  • Find leads matching a query and propose batched status updates

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Nutshell access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Nutshell API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Nutshell changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Nutshell connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Nutshell connector work in claude.ai and Claude Code?
Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Nutshell account, so access always matches what that person can already see and do.
Do I need to host or maintain anything myself?
No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Nutshell's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.
Is it safe to give a coding agent write access to Nutshell?
Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Nutshell account it signs in with. Revoking access is one click in Nutshell.

More on the Nutshell connector

Nutshell connector for claude.aiGoHighLevel + Claude CodeFreshsales + Claude CodeInsightly + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connectorTalk to us